NoizuPromptLingo: Command for Claude Code

.claude/commands/manners.md

manners is a command for Claude Code from noizu-labs-ml/NoizuPromptLingo. It costs 36 tokens per session (394 once invoked), scanned A, original, MIT.

A command that reminds an AI coding assistant to follow the response format defined in a project's CLAUDE.md file. It requires an assumptions table, a section interpreting unstated intent, and an execution-plan diagram.

In plain words
What is it for?
Use it to reset response formatting and require the project's specified planning and assumptions sections in later answers.
Why use it?
It helps restore the expected output structure when the assistant omits required sections or drifts from the project's conventions.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is noizu-labs-ml/NoizuPromptLingo's own configuration. It tells Claude Code how to work on NoizuPromptLingo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything NoizuPromptLingo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to noizu-labs-ml/NoizuPromptLingo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/noizu-labs-ml/NoizuPromptLingo/main/.claude/commands/manners.md
Clone the repo
git clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingo

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for manners

README.md
[![agentmods](https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/manners/github.svg)](https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/manners)
Your own site
<a href="https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/manners"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/manners/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for manners

Your own site · 80×15
<a href="https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/manners"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/manners.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 394 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00394
Opus 5 $0.00018 $0.00197
Sonnet 5 $0.00007 $0.00079
Haiku 4.5 $0.00004 $0.00039

Measured 6d ago against content hash 98e86e98b214, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

manners scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/manners.md · 56 lines

What it actually says

Mind Your Manners

You have been reminded to follow output conventions. Re-read and internalize the following rules, then confirm compliance.

Required Output Sections

Every response must include these three sections — no exceptions, no "this felt casual":

1. Assumptions Table

A markdown table with columns: Open Question, Assumption, Consequence

This shows how you're handling details not explicitly stated by the user, and the impact of each assumption on output.

2. Mind Reading

A mind-reading code fence in which you parse the unstated goals, intention, and mood of the human operator.

Example: what is the user really after? What aren't they saying?

3. Execution Plan

A mermaid flow diagram outlining the route you plan to take to respond to the request.

flowchart TD
    A[Understand request] --> B[Plan approach]
    B --> C[Execute]

When You're Tempted to Skip

  • "This is just a quick question" — include them anyway
  • "This is casual chat" — include them anyway
  • "The sections would be trivial" — include them anyway, even if short
  • "I already answered" — go back and add them

Frankfurt Check

Before output, ask: "Is this bullshit?"

If you're about to skip sections because you've rationalized it — that's bullshit. The contract is the contract.

Acknowledgment

After receiving this command, respond with:

  1. A brief acknowledgment that you've re-read the conventions
  2. Then answer any pending user question with all three sections included
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 56 lines · 36 tokens per session scan A 98e86e98b214

Subscribe to this mod's changes

manners is a command published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 394 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.